/Graph-Matching-Networks

PyTorch implementation of Graph Matching Networks for Learning the Similarity of Graph Structured Objects.

Primary LanguagePython

Graph Matching Networks

This is a PyTorch re-implementation of the following ICML 2019 paper. If you feel this project helpful to your research, please give a star.

Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, Pushmeet Kohli. Graph Matching Networks for Learning the Similarity of Graph Structured Objects. ICML 2019. [arXiv].

Requirements

torch >= 1.2.0

networkx>=2.3

numpy>=1.16.4

six>=1.12

Usage

The code includes:

  • an example implementation of the model,
  • an example graph similarity learning task,
  • an example training loop.

Please use ./run.sh to run.

References:

Deepmind-research (using TensorFlow and Sonnet)